Personne
Matthias Bethge
Cette personne n’est plus à l’EPFL
Publications associées (19)
Contrasting action and posture coding with hierarchical deep neural network models of proprioception
Alexander Mathis, Mackenzie Mathis, Kai Jappe Sandbrink, Matthias Bethge, Pranav Mamidanna
Biological motor control is versatile, efficient, and depends on proprioceptive feedback. Muscles are flexible and undergo continuous changes, requiring distributed adaptive control mechanisms that continuously account for the body's state. The canonical r ...
eLIFE SCIENCES PUBL LTD2023Let's move forward: Image-computable models and a common model evaluation scheme are prerequisites for a scientific understanding of human vision
Martin Schrimpf, Matthias Bethge
In the target article, Bowers et al. dispute deep artificial neural network (ANN) models as the currently leading models of human vision without producing alternatives. They eschew the use of public benchmarking platforms to compare vision models with the ...
Cambridge2023Fixing the problems of deep neural networks will require better training data and learning algorithms
Martin Schrimpf, Adrien Christophe Doerig, Matthias Bethge, Jianghao Liu, Kuntal Ghosh
Bowers et al. argue that deep neural networks (DNNs) are poor models of biological vision because they often learn to rival human accuracy by relying on strategies that differ markedly from those of humans. We show that this problem is worsening as DNNs ar ...
Cambridge2023Pretraining boosts out-of-domain robustness for pose estimation
Alexander Mathis, Mackenzie Mathis, Steffen Schneider, Matthias Bethge, Thomas Ray Biasi, Mert Yüksekgönül
Neural networks are highly effective tools for pose estimation. However, as in other computer vision tasks, robustness to out-of-domain data remains a challenge, especially for small training sets that are common for real-world applications. Here, we probe ...
IEEE COMPUTER SOC2021Task-driven hierarchical deep neural network models of the proprioceptive pathway
Alexander Mathis, Mackenzie Mathis, Kai Jappe Sandbrink, Matthias Bethge, Pranav Mamidanna
Biological motor control is versatile and efficient. Muscles are flexible and undergo continuous changes requiring distributed adaptive control mechanisms. How proprioception solves this problem in the brain is unknown. Here we pursue a task-driven modelin ...
Neuroscience2020Using DeepLabCut for 3D markerless pose estimation across species and behaviors
Alexander Mathis, Mackenzie Mathis, Matthias Bethge, Tanmay Nath, An Chi Chen
Noninvasive behavioral tracking of animals during experiments is critical to many scientific pursuits. Extracting the poses of animals without using markers is often essential to measuring behavioral effects in biomechanics, genetics, ethology, and neurosc ...
2019Pretraining boosts out-of-domain robustness for pose estimation
Alexander Mathis, Mackenzie Mathis, Matthias Bethge, Mert Yüksekgönül
Deep neural networks are highly effective tools for human and animal pose estimation. However, robustness to out-of-domain data remains a challenge. Here, we probe the transfer and generalization ability for pose estimation with two architecture classes (M ...
2019Using DeepLabCut for 3D markerless pose estimation across species and behaviors
Alexander Mathis, Mackenzie Mathis, Matthias Bethge, Tanmay Nath, An Chi Chen
Noninvasive behavioral tracking of animals during experiments is crucial to many scientific pursuits. Extracting the poses of animals without using markers is often essential for measuring behavioral effects in biomechanics, genetics, ethology & neuroscien ...
Neuroscience2018Towards goal-driven deep neural network models to elucidate human arm proprioception
Alexander Mathis, Matthias Bethge, Pranav Mamidanna
Proprioceptive signals are a critical component of our ability to perform complex movements, identify our posture and adapt to environmental changes. Our movements are generated by a large number of muscles and are sensed via a myriad of different receptor ...
2018Markerless tracking of user-defined features with deep learning
Alexander Mathis, Mackenzie Mathis, Matthias Bethge, Pranav Mamidanna
Quantifying behavior is crucial for many applications in neuroscience. Videography provides easy methods for the observation and recording of animal behavior in diverse settings, yet extracting particular aspects of a behavior for further analysis can be h ...
2018